AI Red Team Expert English And Malay

About OpenTrain

OpenTrain AI is the hiring and contracting organization for this role. OpenTrain is the leading platform for finding and building careers in AI training and data labeling, helping contributors discover projects, build a professional profile, and apply for opportunities in minutes.

Creating an OpenTrain account is free, giving you a practical way to grow experience in a rapidly expanding field where human expertise directly shapes how advanced AI systems behave.

About AI Red Teaming

AI red teaming is part of the human side of building safer artificial intelligence. Experts deliberately test conversational models with challenging inputs, evaluate failures, and produce structured feedback that helps improve model behavior.

This work combines adversarial creativity with careful analysis. Your findings can reveal weaknesses involving bias, misinformation, harmful behavior, prompt manipulation, and other safety risks.

The Role

OpenTrain AI is seeking an AI Red Team Expert fluent in English and Malay to conduct adversarial testing of conversational AI models and agents. You will probe systems, surface vulnerabilities, and generate high-quality red team data that supports AI safety improvements.

The project includes sensitive topics such as bias, misinformation, and harmful behaviors. Participation in higher-sensitivity projects is optional and supported by clear guidelines and wellness resources.

• Expert-level contract opportunity
• Remote work available worldwide
• Hourly compensation of $17 to $25
• Default commitment of 40 hours per week, with a listed availability requirement of 20 or more hours weekly
• Part-time contractor engagement

What You'll Do

You will test conversational AI systems systematically and creatively, then turn observed failures into clear, reproducible evidence. Your work will help technical and non-technical stakeholders understand model weaknesses and prioritize safety improvements.

• Red team conversational AI models and agents using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
• Annotate failures, classify vulnerabilities, and flag systemic risks
• Use taxonomies, benchmarks, and playbooks to keep testing consistent
• Document findings in reports, datasets, and attack cases that stakeholders can act on
• Probe sensitive areas including bias, misinformation, and harmful behaviors

Required Qualifications

This role requires prior experience with AI adversarial work, cybersecurity, or socio-technical probing, along with the judgment to test systems rigorously and communicate findings clearly.

• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
• A curious, adversarial mindset and the ability to push systems to breaking points
• A structured approach using frameworks or benchmarks
• Strong communication skills for explaining risks to technical and non-technical stakeholders
• Native fluency in both English and Malay

Helpful Background

Experience in one or more of the following areas can support your work on this project. These backgrounds are helpful rather than additional stated requirements.

• Adversarial machine learning, including jailbreak datasets, prompt injection, RLHF or DPO attacks, and model extraction
• Cybersecurity, including penetration testing, exploit development, or reverse engineering
• Socio-technical risk, including harassment and misinformation probing, abuse analysis, or conversational AI testing
• Creative probing through psychology, acting, or writing for unconventional adversarial thinking

Remote Schedule And Compensation

This is a remote contractor position open worldwide. The role lists a commitment of 20 or more hours per week, with a default project commitment of 40 hours per week.

• Work location: Remote, worldwide
• Engagement: Contractor and part-time
• Schedule: 20 or more hours per week listed; 40 hours per week default
• Pay: $17 to $25 per hour

How To Apply Through OpenTrain

Create a free OpenTrain account, build your AI training profile, and apply for this opportunity in minutes. Your experience in adversarial testing, AI safety, cybersecurity, and bilingual communication can help shape the next generation of conversational AI.

• Highlight English and Malay fluency
• Describe relevant red teaming, cybersecurity, or socio-technical testing experience
• Show examples of structured analysis, vulnerability documentation, or model evaluation
• Review project guidance before participating in sensitive testing work